𝘐𝘵 𝘵𝘰𝘰𝘬 𝘮𝘦 2 𝘺𝘦𝘢𝘳𝘴 𝘵𝘰 𝘨𝘦𝘵 𝘪𝘯𝘵𝘰 𝘮𝘢𝘤𝘩𝘪𝘯𝘦 𝘭𝘦𝘢𝘳𝘯𝘪𝘯𝘨.

Yes, 2 years.

Here some takeaways from my machine learning journey which you can learn from.

(so that you don't spend 2 years like me)

1. You don't need math to get started machine learning

Yes, this is true. However, that doesn't mean math is not important.

It is very important, but the thing is that math can come later on. You can learn it as you go deeper into your machine learning journey.

You'll have to focus on
- Linear Algebra
- Calculus
- Trigonometry
- Algebra
- Statistics
- Probality

Don't be afraid of math, it will come naturally to you as you go.

2. Learn Python (or whichever language you prefer) very very very well!

I cannot stress how important this is.
Machine learning involves a lot of programming and if you are not clear with the fundamentals of programming then you are going to spend 2 years like me. (Please don't)

If you know these topics, then you are good to go with machine learning in Python
- Object oriented programming in Python:Classes, Objects, Methods
- Lists & List functions
- List comprehension
- List slicing
- String formatting
- List, Dictionaries & Tuples

The Basic & Intermediate Python course on freecodecamp can help you get started
Basics : youtube∙com/watch?v=rfscVS0vtbw
Intermediate :youtube∙com/watch?v=HGOBQPFzWKo

3. Have a clear path

Machine learning is a vast field and you must know in which direction you want to go in.
Here's the first course which you must take first!

Machine learning foundations course
youtube∙com/watch?v=_Z9TRANg4c0

> An effective course on getting started with machine learning without all the crazy math,.

Kudos to Lawrence Moroney for designing this brilliant course

4. Practice
Practising you machine learning skills is extremely important. Kaggle is probably the best place to practice your machine learning skills.

You can read more about kaggle here https://twitter.com/PrasoonPratham/status/1325124948025724928?s=20

5. Focus

You have limited time, use it well. If you want to get into machine learning, devote time to it. Don't try to hop in web development, game development along with machine learning.

6. Data cleaning is important, get good at it

When training neural nets, processing clean data through it is a must and data by its very nature is always messy!

You must learn to deal with data well, do not ignore it.

For data cleaning, getting acquainted with numpy and pandas at the start is great idea.
This course will help you get started.

youtube∙com/watch?v=r-uOLxNrNk8

7. Google things when you don't understand something

This is probably the most under rated advice I could give to anyone. We all google things when we don't know something. Don't be afraid of it.

8. You don't need expensive hardware for machine learning

If you think you have a computer that cannot handle machine learning then you are wrong!

Google collab is a jupyter notebook which give you a free GPU running in the cloud which runs in your browser.

Any more excuses?

9. Understand what different frameworks do and use the ones you need.

Remember, you don't need to know all of these at the start, use the ones as per your requirements.

Read this thread for more info https://twitter.com/PrasoonPratham/status/1310103650002378752

10. Have confidence!

Along my journey several people told me that machine learning is something which only scientists with PhDs do.
Wrong!
Anyone can started with machine learning, you just need to have a clear learning path and dedication.

I suggest you read this thread for myths surrounding machine learning https://twitter.com/PrasoonPratham/status/1323890165937438721?s=20

With all that being said, I wish you all the best in your machine learning journey.

It might be tough at the start but you should not give up hope!

Just do it.